© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65629
    Prev
    Next
    INDEX
    Explanations

    anne

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yere
    -0.08
     ders
    -0.08
    услов
    -0.08
     Christianity
    -0.08
    141
    -0.08
     Oil
    -0.08
     Verwaltungs
    -0.08
     mů
    -0.07
    献
    -0.07
     Manuals
    -0.07
    POSITIVE LOGITS
    Observed
    0.08
    特点
    0.08
    Enjoy
    0.07
     camere
    0.07
    approx
    0.07
     architecture
    0.07
    qualities
    0.07
    eneric
    0.07
    integer
    0.07
    amea
    0.07
    Activations Density 0.000%

    No Known Activations